chore(deps): bump js-yaml from 3.14.1 to 3.14.2 in /site in the npm_and_yarn group across 1 directory

.github/workflows/build_and_test.yaml

@@ -184,10 +184,8 @@ jobs:
         include:
           - name: latest
             envoy_gateway_version: v0.0.0-latest
-          - name: v1.6.0-rc.1
-            envoy_gateway_version: v1.6.0-rc.1
-          - name: v1.5.0
-            envoy_gateway_version: v1.5.0
+          - name: v1.6.0
+            envoy_gateway_version: v1.6.0
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-go@v5
@@ -246,7 +244,7 @@ jobs:
       - run: make test-e2e-upgrade
         env:
           # We only need to test the upgrade from the latest stable version of EG.
-          EG_VERSION: v1.6.0-rc.1
+          EG_VERSION: v1.6.0
           K8S_VERSION: ${{ matrix.k8s-version }}
 
   test_e2e_inference_extension:
@@ -275,7 +273,7 @@ jobs:
       - uses: docker/setup-buildx-action@v3
       - run: make test-e2e-inference-extension
         env:
-          EG_VERSION: v1.6.0-rc.1
+          EG_VERSION: v1.6.0
 
   test_e2e_namespaced:
     needs: changes
@@ -305,7 +303,7 @@ jobs:
         env:
           # We only need to test with the latest stable version of EG, since these e2e tests
           # do not depend on the EG version.
-          EG_VERSION: v1.6.0-rc.1
+          EG_VERSION: v1.6.0
 
   test_e2e_aigw:
     needs: changes

Makefile

@@ -14,9 +14,9 @@ GO_TOOL := go tool -modfile=tools/go.mod
 COMMANDS := controller extproc
 
 # This is the package that contains the version information for the build.
-GIT_COMMIT:=$(shell git rev-parse HEAD)
+VERSION_STRING:=$(shell git describe --tags --long)
 VERSION_PACKAGE := github.com/envoyproxy/ai-gateway/internal/version
-GO_LDFLAGS += -X $(VERSION_PACKAGE).Version=$(GIT_COMMIT)
+GO_LDFLAGS += -X $(VERSION_PACKAGE).version=$(VERSION_STRING)
 
 # This is the directory where the built artifacts will be placed.
 OUTPUT_DIR ?= out

api/v1alpha1/ai_gateway_route.go

@@ -328,6 +328,15 @@ type AIGatewayRouteRuleBackendRef struct {
 	// +optional
 	HeaderMutation *HTTPHeaderMutation `json:"headerMutation,omitempty"`
 
+	// BodyMutation defines the request body mutation to be applied to this backend.
+	// This allows modification of JSON fields in the request body before sending to the backend.
+	// When both route-level and backend-level BodyMutation are defined,
+	// route-level takes precedence over backend-level for conflicting operations.
+	// This field is ignored when referencing InferencePool resources.
+	//
+	// +optional
+	BodyMutation *HTTPBodyMutation `json:"bodyMutation,omitempty"`
+
 	// Weight is the weight of the backend. This is exactly the same as the weight in
 	// the BackendRef in the Gateway API. See for the details:
 	// https://gateway-api.sigs.k8s.io/reference/spec/#gateway.networking.k8s.io%2fv1.BackendRef
@@ -398,3 +407,80 @@ type AIGatewayFilterConfigExternalProcessor struct {
 	// +optional
 	Resources *corev1.ResourceRequirements `json:"resources,omitempty"`
 }
+
+// HTTPBodyMutation defines the mutation of HTTP request body JSON fields that will be applied to the request
+type HTTPBodyMutation struct {
+	// Set overwrites/adds the request body with the given JSON field (name, value)
+	// before sending to the backend. Only top-level fields are currently supported.
+	//
+	// Input:
+	//   {
+	//     "model": "gpt-4",
+	//     "service_tier": "default"
+	//   }
+	//
+	// Config:
+	//   set:
+	//   - path: "service_tier"
+	//     value: "scale"
+	//
+	// Output:
+	//   {
+	//     "model": "gpt-4",
+	//     "service_tier": "scale"
+	//   }
+	//
+	// +optional
+	// +listType=map
+	// +listMapKey=path
+	// +kubebuilder:validation:MaxItems=16
+	Set []HTTPBodyField `json:"set,omitempty"`
+
+	// Remove the given JSON field(s) from the HTTP request body before sending to the backend.
+	// The value of Remove is a list of top-level field names to remove.
+	//
+	// Input:
+	//   {
+	//     "model": "gpt-4",
+	//     "service_tier": "default",
+	//     "internal_flag": true
+	//   }
+	//
+	// Config:
+	//   remove: ["service_tier", "internal_flag"]
+	//
+	// Output:
+	//   {
+	//     "model": "gpt-4"
+	//   }
+	//
+	// +optional
+	// +listType=set
+	// +kubebuilder:validation:MaxItems=16
+	Remove []string `json:"remove,omitempty"`
+}
+
+// HTTPBodyField represents a JSON field name and value for body mutation
+type HTTPBodyField struct {
+	// Path is the top-level field name to set in the request body.
+	// Examples: "service_tier", "max_tokens", "temperature"
+	//
+	// +kubebuilder:validation:Required
+	// +kubebuilder:validation:MinLength=1
+	Path string `json:"path"`
+
+	// Value is the JSON value to set at the specified field. This can be any valid JSON value:
+	// string, number, boolean, object, array, or null.
+	// The value will be parsed as JSON and inserted at the specified field.
+	//
+	// Examples:
+	//   - "\"scale\"" (string)
+	//   - "42" (number)
+	//   - "true" (boolean)
+	//   - "{\"key\": \"value\"}" (object)
+	//   - "[1, 2, 3]" (array)
+	//   - "null" (null)
+	//
+	// +kubebuilder:validation:Required
+	Value string `json:"value"`
+}

api/v1alpha1/ai_service_backend.go

@@ -70,6 +70,11 @@ type AIServiceBackendSpec struct {
 	// +optional
 	HeaderMutation *HTTPHeaderMutation `json:"headerMutation,omitempty"`
 
+	// BodyMutation defines the mutation of HTTP request body JSON fields that will be applied to the request
+	// before sending it to the backend.
+	// +optional
+	BodyMutation *HTTPBodyMutation `json:"bodyMutation,omitempty"`
+
 	// TODO: maybe add backend-level LLMRequestCost configuration that overrides the AIGatewayRoute-level LLMRequestCost.
 	// 	That may be useful for the backend that has a different cost calculation logic.
 }

cmd/aigw/README.md

@@ -2,7 +2,7 @@
 
 ## Quick Start
 
-[docker-compose.yml](docker-compose.yaml) builds and runs `aigw`, targeting
+[docker-compose.yaml](docker-compose.yaml) builds and runs `aigw`, targeting
 [Ollama][ollama] for OpenAI chat completion requests on port 1975.
 
 - **aigw** (port 1975): Envoy AI Gateway CLI (standalone mode)

cmd/aigw/config_test.go

@@ -58,16 +58,7 @@ func TestReadConfig(t *testing.T) {
 				"OPENAI_BASE_URL": "http://localhost:11434/v1",
 			},
 			mcpServers:      testMcpServers,
-			expectHostnames: []string{"127.0.0.1.nip.io", "dreamtap.xyz"},
-			expectPort:      "11434",
-		},
-		{
-			name: "generates config from OpenAI env vars for localhost",
-			envVars: map[string]string{
-				"OPENAI_API_KEY":  "test-key",
-				"OPENAI_BASE_URL": "http://localhost:11434/v1",
-			},
-			expectHostnames: []string{"127.0.0.1.nip.io"},
+			expectHostnames: []string{"localhost", "dreamtap.xyz"},
 			expectPort:      "11434",
 		},
 		{

cmd/aigw/main.go

@@ -184,7 +184,7 @@ func doMain(ctx context.Context, stdout, stderr io.Writer, args []string, exitFn
 
 	switch parsed.Command() {
 	case "version":
-		_, _ = fmt.Fprintf(stdout, "Envoy AI Gateway CLI: %s\n", version.Version)
+		_, _ = fmt.Fprintf(stdout, "Envoy AI Gateway CLI: %s\n", version.Parse())
 	case "run", "run <path>":
 		err = rf(ctx, c.Run, c.Run.runOpts, stdout, stderr)
 		if err != nil {

cmd/aigw/run.go

@@ -145,6 +145,10 @@ func run(ctx context.Context, c cmdRun, o *runOpts, stdout, stderr io.Writer) er
 		adminPort:                c.AdminPort,
 		extProcLauncher:          o.extProcLauncher,
 	}
+	// If any of the configured MCP servers is using stdio, set up the streamable HTTP proxies for them
+	if err = proxyStdioMCPServers(ctx, debugLogger, c.mcpConfig); err != nil {
+		return fmt.Errorf("failed to proxy stdio for MCP servers: %w", err)
+	}
 	aiGatewayResourcesYaml, err := readConfig(o.configPath, c.mcpConfig, c.Debug)
 	if err != nil {
 		return err